Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3404 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.8598. Min Range: -4.8598
Max Act: 4.8598. Min Act: -0.1700
Data Index: 1403609 (Open Web Text)
Max Activating Token Index: 25
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.8598. Min Range: -4.8598
Max Act: 4.8286. Min Act: -0.1700
Data Index: 1772206 (Open Web Text)
Max Activating Token Index: 159
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.8598. Min Range: -4.8598
Max Act: 4.8286. Min Act: -0.1700
Data Index: 6931614 (Open Web Text)
Max Activating Token Index: 168
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.8598. Min Range: -4.8598
Max Act: 4.8286. Min Act: -0.1700
Data Index: 1881095 (Open Web Text)
Max Activating Token Index: 18
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.8598. Min Range: -4.8598
Max Act: 4.8286. Min Act: -0.1700
Data Index: 3218013 (Open Web Text)
Max Activating Token Index: 260
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.8598. Min Range: -4.8598
Max Act: 4.8286. Min Act: -0.1700
Data Index: 857292 (Open Web Text)
Max Activating Token Index: 210
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.8598. Min Range: -4.8598
Max Act: 4.7973. Min Act: -0.1700
Data Index: 3670009 (Open Web Text)
Max Activating Token Index: 16
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.8598. Min Range: -4.8598
Max Act: 4.7661. Min Act: -0.1700
Data Index: 3793385 (Open Web Text)
Max Activating Token Index: 209
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.8598. Min Range: -4.8598
Max Act: 4.7973. Min Act: -0.1700
Data Index: 353994 (Open Web Text)
Max Activating Token Index: 23
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.8598. Min Range: -4.8598
Max Act: 4.7973. Min Act: -0.1700
Data Index: 4093867 (Open Web Text)
Max Activating Token Index: 19
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.8598. Min Range: -4.8598
Max Act: 4.7973. Min Act: -0.1700
Data Index: 5359698 (Open Web Text)
Max Activating Token Index: 991
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.8598. Min Range: -4.8598
Max Act: 4.7973. Min Act: -0.1700
Data Index: 2999919 (Open Web Text)
Max Activating Token Index: 228
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.8598. Min Range: -4.8598
Max Act: 4.7661. Min Act: -0.1700
Data Index: 1422170 (Open Web Text)
Max Activating Token Index: 175
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.8598. Min Range: -4.8598
Max Act: 4.7973. Min Act: -0.1700
Data Index: 5749685 (Open Web Text)
Max Activating Token Index: 168
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.8598. Min Range: -4.8598
Max Act: 4.7973. Min Act: -0.1700
Data Index: 5862837 (Open Web Text)
Max Activating Token Index: 670
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.8598. Min Range: -4.8598
Max Act: 4.7973. Min Act: -0.1700
Data Index: 1186310 (Open Web Text)
Max Activating Token Index: 17
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.8598. Min Range: -4.8598
Max Act: 4.7973. Min Act: -0.1700
Data Index: 8721127 (Open Web Text)
Max Activating Token Index: 157
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.8598. Min Range: -4.8598
Max Act: 4.7973. Min Act: -0.1700
Data Index: 2398731 (Open Web Text)
Max Activating Token Index: 262
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.8598. Min Range: -4.8598
Max Act: 4.7973. Min Act: -0.1700
Data Index: 1364659 (Open Web Text)
Max Activating Token Index: 907
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.8598. Min Range: -4.8598
Max Act: 4.7661. Min Act: -0.1700
Data Index: 553048 (Open Web Text)
Max Activating Token Index: 210
Click toggle to see full text
Truncated
Full Text #19